Skip to content
conftrace_

deep network training

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

weight decay (2) neural network optimization (2) adaptive weight shrink (1) unitary neural network (1) orthogonal convolutional network (1) rank-k update (1) adaptive gradient algorithm (1) learning rate modulation (1) satisfiability modulo theories (1) neural network (1)

Papers

Win: Weight-Decay-Integrated Nesterov Acceleration for Adaptive Gradient Algorithms ICLR 2023 projUNN: efficient method for training deep networks with unitary matrices NeurIPS 2022 Reducing Neural Network Parameter Initialization Into an SMT Problem (Student Abstract) AAAI 2021 SAdam: A Variant of Adam for Strongly Convex Functions ICLR 2020 Understanding the Disharmony between Weight Normalization Family and Weight Decay AAAI 2020 All You Need Is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks With Orthonormality and Modulation CVPR 2017